Tag “mcpserver #ocr #agents #mcpservers” — 5

libofcongress-mcp-server

smithery.ai

Search LOC digital collections, Chronicling America newspapers (full OCR), and LC Subject Headings.

Ladislav Hejdánek

smithery.ai

Explore the digital archive of Czech philosopher Ladislav Hejdánek through semantic search and full-text retrieval. Access complete OCR texts of historical documents categorized by type and language. Streamline philosophical research by finding relevant passages and insights across the entire collection.

Receipt Extraction

smithery.ai

AU GST/ABN-aware receipt & invoice extraction — applies documented AU entertainment/ITC tax-code rules per line item, returning a `tax_code`, a `confidence` and a `rationale` for each, not just OCR. Vendor, line items, totals, and tax fields as structured, validated JSON. **How it works:** caller-supplied documents in, versioned JSON out. Declared output schema (`structuredContent`), per-document error isolation, honest confidence signals. **Free tier:** 20 documents/month,

Handwriting OCR

smithery.ai

Integrate your applications with the Handwriting OCR service to effortlessly upload documents, check their processing status, and retrieve OCR results in Markdown format. Enhance your workflows by automating text extraction from images and PDFs with ease.

docu-scan by SPOCONT

smithery.ai

Extract specified key-values and all recognizable structured data from .pdf using direct read and OCR read tools and retrieve in a .json. This is also useful to automatize contract, invoice, other document procession for accounting, comparision or automated form / api feeding.